param dim_i, dim_o loss opti dim_sample bwd_σ value dim_i=20 dim_o=30 mse mse+cos mse+dot hetero2 all adam, lr=1e-4 adam, lr=1e-3 adam, lr=1e-2 all 2^0 2^-2 2^-4 2^-6 2^-8 all loglinexp all hide external loss show external loss hide loss (mse) show loss (mse) hide loss (cos) show loss (cos) hide loss (dot) show loss (dot) hide loss (dot_sim) show loss (dot_sim)